[llvm] 49bac13 - [CostModel][X86] Add test coverage for rint/lrint/llrint fp calls

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2024-05-02T18:51:35+01:00
New Revision: 49bac13acdb8159d8b257059a72742bb3c0ec196

URL: https://github.com/llvm/llvm-project/commit/49bac13acdb8159d8b257059a72742bb3c0ec196
DIFF: https://github.com/llvm/llvm-project/commit/49bac13acdb8159d8b257059a72742bb3c0ec196.diff

LOG: [CostModel][X86] Add test coverage for rint/lrint/llrint fp calls

Added: 
    

Modified: 
    llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
    llvm/test/Analysis/CostModel/X86/arith-fp-latency.ll
    llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
    llvm/test/Analysis/CostModel/X86/arith-fp.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll b/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
index 749e239c33ad6c..5247ef0cbd707b 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp-codesize.ll
@@ -616,6 +616,147 @@ define i32 @fma(i32 %arg) {
   ret i32 undef
 }
 
+define i32 @rint(i32 %arg) {
+; SSE1-LABEL: 'rint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'rint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'rint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call float @llvm.rint.f32.f32(float undef)
+  %V4F32 = call <4 x float> @llvm.rint.v4f32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x float> @llvm.rint.v8f32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x float> @llvm.rint.v16f32.v16f32(<16 x float> undef)
+
+  %F64 = call double @llvm.rint.f64.f64(double undef)
+  %V2F64 = call <2 x double> @llvm.rint.v2f64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x double> @llvm.rint.v4f64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x double> @llvm.rint.v8f64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @lrint(i32 %arg) {
+; SSE1-LABEL: 'lrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'lrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'lrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+  %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+
+  %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+  %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @llrint(i32 %arg) {
+; SSE1-LABEL: 'llrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'llrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'llrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+  %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+
+  %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+  %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
 declare float @llvm.sqrt.f32(float)
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp-latency.ll b/llvm/test/Analysis/CostModel/X86/arith-fp-latency.ll
index 0f4bf2896559b3..3f4ecdf340d81b 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp-latency.ll
@@ -1012,6 +1012,279 @@ define i32 @fma(i32 %arg) {
   ret i32 undef
 }
 
+define i32 @rint(i32 %arg) {
+; SSE1-LABEL: 'rint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'rint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'rint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'rint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'rint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'rint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'rint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call float @llvm.rint.f32.f32(float undef)
+  %V4F32 = call <4 x float> @llvm.rint.v4f32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x float> @llvm.rint.v8f32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x float> @llvm.rint.v16f32.v16f32(<16 x float> undef)
+
+  %F64 = call double @llvm.rint.f64.f64(double undef)
+  %V2F64 = call <2 x double> @llvm.rint.v2f64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x double> @llvm.rint.v4f64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x double> @llvm.rint.v8f64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @lrint(i32 %arg) {
+; SSE1-LABEL: 'lrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'lrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'lrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'lrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'lrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'lrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'lrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+  %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+
+  %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+  %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @llrint(i32 %arg) {
+; SSE1-LABEL: 'llrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'llrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'llrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'llrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'llrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'llrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'llrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+  %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+
+  %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+  %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
 declare float @llvm.sqrt.f32(float)
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
index 90b7feb77cf8ad..8040675bef9c5c 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp-sizelatency.ll
@@ -946,6 +946,279 @@ define i32 @fma(i32 %arg) {
   ret i32 undef
 }
 
+define i32 @rint(i32 %arg) {
+; SSE1-LABEL: 'rint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'rint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'rint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'rint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'rint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'rint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'rint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call float @llvm.rint.f32.f32(float undef)
+  %V4F32 = call <4 x float> @llvm.rint.v4f32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x float> @llvm.rint.v8f32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x float> @llvm.rint.v16f32.v16f32(<16 x float> undef)
+
+  %F64 = call double @llvm.rint.f64.f64(double undef)
+  %V2F64 = call <2 x double> @llvm.rint.v2f64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x double> @llvm.rint.v4f64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x double> @llvm.rint.v8f64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @lrint(i32 %arg) {
+; SSE1-LABEL: 'lrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'lrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'lrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'lrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'lrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'lrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'lrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+  %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+
+  %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+  %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @llrint(i32 %arg) {
+; SSE1-LABEL: 'llrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'llrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'llrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'llrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'llrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'llrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'llrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+  %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+
+  %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+  %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
 declare float @llvm.sqrt.f32(float)
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-fp.ll b/llvm/test/Analysis/CostModel/X86/arith-fp.ll
index ae3b5d7cddb2eb..17bd223affa1d0 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-fp.ll
@@ -1089,6 +1089,279 @@ define i32 @fma(i32 %arg) {
   ret i32 undef
 }
 
+define i32 @rint(i32 %arg) {
+; SSE1-LABEL: 'rint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'rint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'rint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'rint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'rint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'rint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'rint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %F32 = call float @llvm.rint.f32.f32(float undef)
+  %V4F32 = call <4 x float> @llvm.rint.v4f32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x float> @llvm.rint.v8f32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x float> @llvm.rint.v16f32.v16f32(<16 x float> undef)
+
+  %F64 = call double @llvm.rint.f64.f64(double undef)
+  %V2F64 = call <2 x double> @llvm.rint.v2f64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x double> @llvm.rint.v4f64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x double> @llvm.rint.v8f64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @lrint(i32 %arg) {
+; SSE1-LABEL: 'lrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'lrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'lrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'lrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'lrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'lrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'lrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %F32 = call i32 @llvm.lrint.i32.f32(float undef)
+  %V4F32 = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i32> @llvm.lrint.v16i32.v16f32(<16 x float> undef)
+
+  %F64 = call i32 @llvm.lrint.i32.f64(double undef)
+  %V2F64 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
+define i32 @llrint(i32 %arg) {
+; SSE1-LABEL: 'llrint'
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE2-LABEL: 'llrint'
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE42-LABEL: 'llrint'
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'llrint'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'llrint'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'llrint'
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'llrint'
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %F32 = call i64 @llvm.llrint.i64.f32(float undef)
+  %V4F32 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+  %V8F32 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+  %V16F32 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+
+  %F64 = call i64 @llvm.llrint.i64.f64(double undef)
+  %V2F64 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
+  %V4F64 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+  %V8F64 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+
+  ret i32 undef
+}
+
 declare float @llvm.sqrt.f32(float)
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)